Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8012
    Prev
    Next
    INDEX
    Explanations

    academic scientific fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     different
    -1.08
     this
    -1.07
     their
    -1.01
     various
    -1.00
     numerous
    -0.97
     производится
    -0.96
    ときは
    -0.94
    場所で
    -0.94
    あー
    -0.93
     dozens
    -0.92
    POSITIVE LOGITS
    forschung
    1.20
     research
    1.02
     pesquisas
    0.97
    letoe
    0.97
     textbooks
    0.96
    applied
    0.93
     التطبيق
    0.93
     Aplica
    0.92
     مسائل
    0.91
    techniques
    0.91
    Activations Density 0.147%

    No Known Activations